© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211021
    Prev
    Next
    INDEX
    Explanations

    established rights

    np_acts-logits-general · gemini-2.5-flash-lite

    mountain view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realizzato
    0.49
    飭
    0.46
    所以
    0.46
    സ്
    0.44
     accessori
    0.44
    Has
    0.44
    ധ്യമ
    0.43
    த்தில்
    0.43
    お
    0.42
     سای
    0.42
    POSITIVE LOGITS
    $\--
    0.49
     পেরিয়ে
    0.45
     கண
    0.44
    jär
    0.44
    
    0.44
    )=[
    0.43
    cnt
    0.42
    ⼀
    0.42
    centred
    0.42
    }^{+}(
    0.42
    Activations Density 0.000%

    No Known Activations